DeepSeek/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(compaction): flag missing snapshot coverage with a FIXME

Browse Source 
The compaction e2e is the only coverage of runaway compaction; there is
no keyless full-transcript snapshot. Record why in a FIXME on the e2e
module doc: dsh-llm-replay rebuilds one model call per (turn, step) from
assistant/chunk events, but summarize() assembles its stream locally and
appends none, so the interleaved summarization call is unreplayable until
the replay harness can serve it.
This commit is contained in:
Tianyi Cui
2026-07-02 00:29:33 +08:00
parent b115b2b4ac
commit 58b86839af
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/coding-agent/tests/compaction.e2e.ts
View File

@@ -18,6 +18,13 @@ import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.
* landed in the real session log, the surface actually shrank (a replace node
* exists and shadowed older nodes), and the agent still produced a final answer
* after compaction (so the summarized history did not break the conversation).
*
* FIXME(compaction-snapshot): this key-gated e2e is the ONLY coverage of runaway
* compaction — there is no keyless full-transcript snapshot of it. dsh-llm-replay
* reconstructs one model call per (turn, step) from `assistant/chunk` events, but
* `summarize()` assembles its stream into a local BlockAssembler and appends no
* `assistant/chunk`, so the interleaved summarization call is unreplayable. A
* snapshot needs replay-harness work to serve that call; deferred as a follow-up.
*/
let workdir: string | undefined